{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B6MPFISKKADPVICB5RNHWEDOMM","short_pith_number":"pith:B6MPFISK","schema_version":"1.0","canonical_sha256":"0f98f2a24a5006faa041ec5a7b106e631968894ad51b032a71d8574952a3bd5b","source":{"kind":"arxiv","id":"2410.20774","version":2},"attestation_state":"computed","paper":{"title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongryeol Lee, Joonsuk Park, Kyomin Jung, Yerin Hwang, Yongil Kim","submitted_at":"2024-10-28T06:21:43Z","abstract_excerpt":"In line with the principle of honesty, there has been a growing effort to train large language models (LLMs) to generate outputs containing epistemic markers. However, evaluation in the presence of epistemic markers has been largely overlooked, raising a critical question: Could the use of epistemic markers in LLM-generated outputs lead to unintended negative consequences? To address this, we present EMBER, a benchmark designed to assess the robustness of LLM-judges to epistemic markers in both single and pairwise evaluation settings. Our findings, based on evaluations using EMBER, reveal that"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.20774","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-28T06:21:43Z","cross_cats_sorted":[],"title_canon_sha256":"00dd55c1762b1fa60a256539e0a2a135390a7d95636059954659284ac57c5f37","abstract_canon_sha256":"e36f30bde2286e6a8d9e777cb3ef365e29f1a3cac14562be74972ce238dc0644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:35.107591Z","signature_b64":"ytm0d+vCAAMiLG/WjBnrrSbRCdnQKzLa16LpwNg149a4axZTzUILnEaoLbs34fjv70T2YCMVr6sWtj6kceHyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f98f2a24a5006faa041ec5a7b106e631968894ad51b032a71d8574952a3bd5b","last_reissued_at":"2026-07-05T10:56:35.107026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:35.107026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongryeol Lee, Joonsuk Park, Kyomin Jung, Yerin Hwang, Yongil Kim","submitted_at":"2024-10-28T06:21:43Z","abstract_excerpt":"In line with the principle of honesty, there has been a growing effort to train large language models (LLMs) to generate outputs containing epistemic markers. However, evaluation in the presence of epistemic markers has been largely overlooked, raising a critical question: Could the use of epistemic markers in LLM-generated outputs lead to unintended negative consequences? To address this, we present EMBER, a benchmark designed to assess the robustness of LLM-judges to epistemic markers in both single and pairwise evaluation settings. Our findings, based on evaluations using EMBER, reveal that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20774","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.20774/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.20774","created_at":"2026-07-05T10:56:35.107086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20774v2","created_at":"2026-07-05T10:56:35.107086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20774","created_at":"2026-07-05T10:56:35.107086+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6MPFISKKADP","created_at":"2026-07-05T10:56:35.107086+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6MPFISKKADPVICB","created_at":"2026-07-05T10:56:35.107086+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6MPFISK","created_at":"2026-07-05T10:56:35.107086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM","json":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM.json","graph_json":"https://pith.science/api/pith-number/B6MPFISKKADPVICB5RNHWEDOMM/graph.json","events_json":"https://pith.science/api/pith-number/B6MPFISKKADPVICB5RNHWEDOMM/events.json","paper":"https://pith.science/paper/B6MPFISK"},"agent_actions":{"view_html":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM","download_json":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM.json","view_paper":"https://pith.science/paper/B6MPFISK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20774&json=true","fetch_graph":"https://pith.science/api/pith-number/B6MPFISKKADPVICB5RNHWEDOMM/graph.json","fetch_events":"https://pith.science/api/pith-number/B6MPFISKKADPVICB5RNHWEDOMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM/action/storage_attestation","attest_author":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM/action/author_attestation","sign_citation":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM/action/citation_signature","submit_replication":"https://pith.science/pith/B6MPFISKKADPVICB5RNHWEDOMM/action/replication_record"}},"created_at":"2026-07-05T10:56:35.107086+00:00","updated_at":"2026-07-05T10:56:35.107086+00:00"}